Pavement structure layer thickness calculation method and system based on ground penetrating radar

Abstract

The invention discloses a ground penetrating radar-based pavement structure layer thickness calculation method and system, and belongs to the technical field of road engineering pavement maintenance. The method comprises the following steps: acquiring a road radar map, and identifying a pavement structure layer by using a YOLOv8 model; calculating the thickness of the structural layer through OpenCV; for the thickness abnormal position, extracting corresponding electromagnetic data and tracking the maximum amplitude point in the horizon range, and correcting the thickness value in combination with DBSCAN clustering; and importing a whole-section thickness result into post-processing software to generate a continuous horizon curved surface, and counting average thickness data of different length sections. And the system executes the steps. The problems that traditional core drilling sampling is low in efficiency and radar data manual processing cost is high are solved, automatic nondestructive detection and anomaly correction of the pavement thickness are achieved, and accurate data support is provided for maintenance design.

Description

Technical Field

[0001] The present invention belongs to the technical field of road engineering pavement maintenance, and in particular relates to a method and system for calculating the thickness of a pavement structure layer based on ground penetrating radar. Background Art

[0002] In the field of road engineering pavement maintenance, accurate detection of asphalt structural layer thickness is a core indicator for evaluating construction quality and formulating maintenance plans. Currently, the industry mainly adopts two types of technical solutions: Traditional core sampling method: directly measuring the thickness by physically drilling core samples of the road surface. This method has obvious drawbacks: The detection efficiency is low and it is difficult to meet the needs of large-scale road detection; The sampling points are not representative enough to reflect the overall thickness distribution of the road section; Damage to the structural integrity of the pavement may cause secondary diseases.

[0003] Ground-penetrating radar (GPR) nondestructive testing technology: As a nondestructive method, it has been widely used in road disease diagnosis and structural layer thickness and moisture content testing. However, as the mileage of inspections increases, this technology has exposed the following bottlenecks: Data processing is highly manual: professional engineers are required to interpret radar images, consuming a large amount of human resources; Lack of standardization of results: The interpretation process is influenced by subjective experience, and the output of different operators is inconsistent; Long-mileage inspection efficiency is limited: Faced with massive amounts of radar data (such as a single inspection generating 320 channels of electromagnetic data), manual processing makes it difficult to achieve efficient batch analysis.

[0004] The above problems result in the existing technology being unable to meet the requirements for automation, standardization and efficiency of thickness detection in pavement maintenance. Summary of the Invention

[0005] The present invention provides a method and system for calculating the thickness of pavement structure layers based on ground-penetrating radar. It automatically identifies pavement structure layers in radar maps through the YOLOv8 algorithm and automatically calculates the thickness in combination with OpenCV, completely replacing the traditional method of manually interpreting radar data, significantly reducing labor costs and processing time. It is particularly suitable for large-scale road inspection projects, thereby effectively solving at least one technical problem involved in the background technology.

[0006] To achieve the above object, the technical solution of the present invention is: A method for calculating the thickness of a pavement structure layer based on ground penetrating radar comprises the following steps: Step S1, obtaining radar spectra and corresponding electromagnetic data generated by ground penetrating radar for road detection; Step S2, using the YOLOv8 model to identify the pavement structure layer in the radar map; Step S3, determining a size reference object based on the known thickness in the radar map; Step S4, using OpenCV to calculate the pixel size of each structural layer in the radar map, and converting the actual thickness value based on the size reference; Step S5, performing abnormal processing on the abnormal thickness identification position: Step S51, extracting electromagnetic data corresponding to the abnormal position; Step S52, tracking the maximum point of the absolute value of the amplitude of the single-channel electromagnetic wave within the layer depth range; Step S53, DBSCAN clustering is performed on the layer points of the 320 electromagnetic waves; Step S54, calculating the actual thickness of the abnormal position based on the clustering result; Step S6: Integrate all thickness identification results to generate a continuous layer surface.

[0007] Optionally, before step S2, the following steps may be further included: Collect road radar detection data to establish thickness recognition dataset; The best weight model is obtained based on the YOLOv8s model training dataset.

[0008] Optionally, in step S4, the size reference is a known road surface thickness marked in the radar map.

[0009] Optionally, in step S52: The depth range of the horizon is determined by back-calculating the normal thickness value adjacent to the abnormal position. The calculation formula is: tracking_range = [min-20, max+20]; Where min and max are the depth points corresponding to the adjacent left and right normal thicknesses respectively.

[0010] Optionally, after step S6, the following steps may be further performed: Calculate the average thickness in sections with preset lengths, where the section lengths include 5m, 10m, 100m and 1000m; Generate thickness variation curve and result file.

[0011] The present invention also provides a pavement structure layer thickness calculation system based on ground penetrating radar, which is used to execute the method described above, including: Data acquisition module, used to collect radar maps and electromagnetic data; Layer recognition module, equipped with the YOLOv8 model to identify structural layers in radar images; Thickness calculation module, which converts the actual thickness based on the size reference object through OpenCV; Exception handling module, configured as: Extract electromagnetic data of abnormal locations; Track the maximum point of the absolute value of the electromagnetic wave amplitude within the depth range of the layer; Perform DBSCAN clustering on 320 layer points and calculate thickness; Output module, integrates thickness data to generate continuous layer surface and segmented statistical reports.

[0012] Optionally, the output module is further configured as follows: Calculate the average thickness by length of 5m, 10m, 100m and 1000m; Output thickness variation curve and corresponding result file.

[0013] The present invention also provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.

[0014] The present invention also provides a computer-readable storage medium storing a computer program, which implements the steps of the method when executed by a processor.

[0015] The beneficial effects of the present invention are as follows: 1. This invention uses the YOLOv8 algorithm to automatically identify the pavement structure layer in the radar map and combines it with OpenCV to automatically calculate the thickness, completely replacing the traditional method of manually interpreting radar data, significantly reducing labor costs and processing time, and is particularly suitable for large-scale road inspection projects.

[0016] 2. The present invention adopts ground penetrating radar non-destructive testing technology to avoid physical damage to the road surface caused by core sampling. At the same time, it overcomes the defects of poor representativeness and sparse detection points of core sampling, and realizes continuous thickness analysis of the entire road section.

[0017] 3. The present invention addresses layer identification anomalies (such as outliers or unidentified layers): by tracking the maximum amplitude point of the electromagnetic signal within the layer range, the structural layer boundary is accurately located; combined with the DBSCAN clustering algorithm, outlier correction is performed on 320 data channels to effectively eliminate interference and ensure the stability of the thickness calculation results (the embodiment shows an error of only 0.2% to 1.1%).

[0018] 4. The present invention imports the identification results into post-processing software to generate a continuous thickness layer surface, which intuitively displays the spatial changes of the pavement structure; supports multi-scale thickness statistical analysis such as 5m, 10m, 100m, and 1000m, outputs data files and change curves, and accurately guides the formulation of maintenance plans (such as locating weak sections).

[0019] 5. The deviation between the OpenCV calculation results and the coring measured values ​​in the embodiment of the present invention is less than 1.1%, and is highly consistent with the results of the radar post-processing software, which confirms the reliability and applicability of the method in engineering scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive work, among which: Figure 1 A flow chart of a method for calculating the thickness of a pavement structure layer based on ground penetrating radar provided by the present invention; Figure 2 The radar map provided by the present invention; Figure 3 This is a schematic diagram of the pavement structure layer division provided by the present invention. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0022] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0023] In addition, the terms "first," "second," and so on, used in this disclosure are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referenced. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this disclosure, "plurality" means at least two, such as two or three, unless otherwise specifically defined.

[0024] In the present invention, unless otherwise specified or limited, the terms "connection" and "fixation" should be understood in a broad sense. For example, "fixation" can refer to fixed connection, detachable connection, or integration; it can refer to mechanical connection; it can refer to direct connection or indirect connection through an intermediate medium; it can refer to internal communication between two elements or interaction between two elements, unless otherwise specified. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0025] In addition, the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in this field can implement it. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0026] See also Figure 1 As shown, an embodiment of the present invention provides a method for calculating the thickness of a pavement structure layer based on ground penetrating radar, comprising the following steps: Step S1, obtaining radar spectra and corresponding electromagnetic data generated by ground penetrating radar for road detection; Step S2, using the YOLOv8 model to identify the pavement structure layer in the radar map; Step S3, determining a size reference object based on the known thickness in the radar map; Step S4, using OpenCV to calculate the pixel size of each structural layer in the radar map, and converting the actual thickness value based on the size reference; Step S5, performing abnormal processing on the abnormal thickness identification position: Step S51, extracting electromagnetic data corresponding to the abnormal position; Step S52, tracking the maximum point of the absolute value of the amplitude of the single-channel electromagnetic wave within the layer depth range; Step S53, DBSCAN clustering is performed on the layer points of the 320 electromagnetic waves; Step S54, calculating the actual thickness of the abnormal position based on the clustering result; Step S6: Integrate all thickness identification results to generate a continuous layer surface.

[0027] Before step S2, the following steps are also included: Collect road radar detection data to establish thickness recognition dataset; The best weight model is obtained based on the YOLOv8s model training dataset.

[0028] In step S4, the size reference is the known road surface thickness marked in the radar map.

[0029] In step S52: The depth range of the horizon is determined by back-calculating the normal thickness value adjacent to the abnormal position. The calculation formula is: tracking_range = [min-20, max+20]; Where min and max are the depth points corresponding to the adjacent left and right normal thicknesses respectively.

[0030] After step S6, the following steps are also included: Calculate the average thickness in sections with preset lengths, where the section lengths include 5m, 10m, 100m and 1000m; Generate thickness variation curve and result file.

[0031] The present invention also provides a pavement structure layer thickness calculation system based on ground penetrating radar, which is used to execute the method described above, and includes a data acquisition module, a layer recognition module, a thickness calculation module and an exception processing module.

[0032] The data acquisition module is used to collect radar spectra and electromagnetic data.

[0033] The layer recognition module is equipped with a YOLOv8 model to identify structural layers in radar images.

[0034] The thickness calculation module converts the actual thickness based on the size reference object through OpenCV.

[0035] The exception handling module is configured as follows: Extract electromagnetic data of abnormal locations; Track the maximum point of the absolute value of the electromagnetic wave amplitude within the depth range of the layer; Perform DBSCAN clustering on 320 layer points and calculate thickness; Output module, integrates thickness data to generate continuous layer surface and segmented statistical reports.

[0036] The output module is further configured as follows: Calculate the average thickness by length of 5m, 10m, 100m and 1000m; Output thickness variation curve and corresponding result file.

[0037] The pavement structure layer thickness calculation method based on ground penetrating radar provided by the present invention is described in detail below with reference to specific embodiment 1.

[0038] Example 1 Example 1 provides a method for calculating the thickness of a pavement structure layer based on ground penetrating radar, comprising the following steps: Step S1: Obtain radar spectrum generated by ground penetrating radar for road detection (see Figure 2 shown) and corresponding electromagnetic data; Step S2: Use the YOLOv8 model to identify the pavement structure layers in the radar map (see Figure 3 shown); Step S3, determining a size reference object based on the known thickness in the radar map; Step S4: Use OpenCV to calculate the pixel size of each structural layer in the radar map and convert it into actual thickness using a dimensional reference. The thicknesses of the structural layers from top to bottom are 7.4in, 14.6in, and 23.0in, which translate to 18.79cm, 37.08cm, and 58.42cm in centimeters. The post-processing software outputs are 19cm, 37cm, and 59cm, respectively. Field coring verified that the actual core sample thicknesses are 19cm for the surface layer, 37cm for the upper base layer, and 58cm for the lower base layer. The deviations between the OpenCV-based calculations and the actual surface, upper, and lower base layer thicknesses are 1.1%, 0.2%, and 0.7%, respectively. Step S5, performing abnormal processing on the abnormal thickness identification position: Step S51, extracting electromagnetic data corresponding to the abnormal position; Step S52, tracking the maximum point of the absolute value of the amplitude of the single-channel electromagnetic wave within the layer depth range; Step S53, DBSCAN clustering is performed on the layer points of the 320 electromagnetic waves; Step S54, calculating the actual thickness of the abnormal position based on the clustering result; Step S6: Integrate all thickness identification results to generate a continuous layer surface.

[0039] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are protected by the present invention.

Claims

1. A method for calculating the thickness of a pavement structure layer based on ground penetrating radar, characterized in that: The following steps are involved: Step S1, obtaining radar spectra and corresponding electromagnetic data generated by ground penetrating radar for road detection; Step S2, using the YOLOv8 model to identify the pavement structure layer in the radar map; Step S3, determining a size reference object based on the known thickness in the radar map; Step S4, using OpenCV to calculate the pixel size of each structural layer in the radar map, and converting the actual thickness value based on the size reference; Step S5, performing abnormal processing on the abnormal thickness identification position: Step S51, extracting electromagnetic data corresponding to the abnormal position; Step S52, tracking the maximum point of the absolute value of the amplitude of the single-channel electromagnetic wave within the layer depth range; Step S53, DBSCAN clustering is performed on the layer points of the 320 electromagnetic waves; Step S54, calculating the actual thickness of the abnormal position based on the clustering result; Step S6: Integrate all thickness identification results to generate a continuous layer surface.

2. The method according to claim 1, characterized in that Before step S2, the following steps are also included: Collect road radar detection data to establish thickness recognition dataset; The best weight model is obtained based on the YOLOv8s model training dataset.

3. The method according to claim 1, characterized in that In step S4, the size reference is the known road surface thickness marked in the radar map.

4. The method according to claim 1, wherein In step S52: The depth range of the horizon is determined by back-calculating the normal thickness value adjacent to the abnormal position. The calculation formula is: tracking_range = [min-20, max+20]; Where min and max are the depth points corresponding to the adjacent left and right normal thicknesses respectively.

5. The method according to claim 1, wherein After step S6, the method further includes: Calculate the average thickness in sections with preset lengths, where the section lengths include 5m, 10m, 100m and 1000m; Generate thickness variation curve and result file.

6. A pavement structure layer thickness calculation system based on ground penetrating radar, used to execute the method according to any one of claims 1 to 5, characterized in that: include: Data acquisition module, used to collect radar maps and electromagnetic data; Layer recognition module, equipped with the YOLOv8 model to identify structural layers in radar images; Thickness calculation module, which converts the actual thickness based on the size reference object through OpenCV; Exception handling module, configured as: Extract electromagnetic data of abnormal locations; Track the maximum point of the absolute value of the electromagnetic wave amplitude within the depth range of the layer; Perform DBSCAN clustering on 320 layer points and calculate thickness; Output module, integrates thickness data to generate continuous layer surface and segmented statistical reports.

7. The system according to claim 6, characterized in that The output module is further configured as follows: Calculate the average thickness by length of 5m, 10m, 100m and 1000m; Output thickness variation curve and corresponding result file.

Images